Configural processing as an optimized strategy for robust object recognition in neural networks

TL;DR

This study demonstrates that neural networks utilizing configural cues, which encode spatial relationships among object parts, achieve more robust object recognition under transformations than those relying solely on local features, and this occurs in a purely feedforward manner.

Contribution

The paper provides neurocomputational evidence that configural processing enhances robustness in object recognition within neural networks, emerging naturally without recurrent mechanisms.

Findings

Configural cues improve robustness to geometric transformations.

Configural processing emerges later than local features in network layers.

Feedforward configural processing benefits naturalistic face recognition.

Abstract

Configural processing, the perception of spatial relationships among an object's components, is crucial for object recognition. However, the teleology and underlying neurocomputational mechanisms of such processing are still elusive, notwithstanding decades of research. We hypothesized that processing objects via configural cues provides a more robust means to recognizing them relative to local featural cues. We evaluated this hypothesis by devising identification tasks with composite letter stimuli and comparing different neural network models trained with either only local or configural cues available. We found that configural cues yielded more robust performance to geometric transformations such as rotation or scaling. Furthermore, when both features were simultaneously available, configural cues were favored over local featural cues. Layerwise analysis revealed that the sensitivity to configural cues emerged later relative to local feature cues, possibly contributing to the robustness to pixel-level transformations. Notably, this configural processing occurred in a purely feedforward manner, without the need for recurrent computations. Our findings with letter stimuli were successfully extended to naturalistic face images. Thus, our study provides neurocomputational evidence that configural processing emerges in a na\"ive network based on task contingencies, and is beneficial for robust object processing under varying viewing conditions.